Oriol Nieto

Thanks for your reply, I will try out the keras1 branch.

Great, thanks! On Thu, Feb 16, 2017 at 8:20 PM, Eder Santana wrote: > Hi @oarriaga thanks for all the help! > I think you can write the it all...

We used keras 2.7.0, and Python 3.8.10. Maybe we should add this in the `setup.py` or create an `environment.yml` file so that users can more easily replicate our environment. Thanks...

I have merged a PR with a new set of instructions and dependencies (https://github.com/justinsalamon/musicseg_deepemb/pull/5). Please, give it a try (make sure you're using Keras 2.6 and Python 3.7, as indicated...

Apologies for the huge delay. I just re-ran the tests and they are all passing on my macOS arm64 machine: ``` ❯ python -m unittest test_equivalence /Users/onieto/micromamba/envs/convspec/lib/python3.9/site-packages/librosa/util/files.py:12: DeprecationWarning: pkg_resources is...

You can find JAMS parsers for several datasets here https://github.com/marl/jams-data/tree/master/parsers I'm not familiar with the Robbie Williams dataset, but we should write a new parser for it and put it...

Will work on this over the weekend. On Wed, Feb 3, 2016 at 5:27 AM Brian McFee [email protected] wrote: > Assigned #9 https://github.com/marl/jams-data/issues/9 to @urinieto > https://github.com/urinieto. > > —...

I finished points 1, 2 and 3. I don't have the cycles for tackling 4 right now (maybe we can do some hacking in Dagstuhl @bmcfee ?). Let me know...

Alright!

Good point. I think in terms of annotations this should be enough. I am probably gonna compute the features with the new msaf 0.1.0 format, but this shouldn't have any...